CN111445451B - Brain image processing method, system, computer device and storage medium - Google Patents
Brain image processing method, system, computer device and storage medium Download PDFInfo
- Publication number
- CN111445451B CN111445451B CN202010200838.0A CN202010200838A CN111445451B CN 111445451 B CN111445451 B CN 111445451B CN 202010200838 A CN202010200838 A CN 202010200838A CN 111445451 B CN111445451 B CN 111445451B
- Authority
- CN
- China
- Prior art keywords
- brain
- region
- brain image
- image
- processed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Epidemiology (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application relates to a brain image processing method, a brain image processing system, a computer device and a storage medium. The method comprises the following steps: acquiring a brain image to be processed; inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image; inputting the brain image into a preset second separation network to obtain each brain region division map corresponding to the brain image; and analyzing the region of interest map and each brain region division map to obtain a preliminary grading result of the brain image. The method can improve the diagnosis efficiency of the brain image to be processed.
Description
Technical Field
The present application relates to the field of brain image processing, and in particular, to a brain image processing method, system, computer device, and storage medium.
Background
Stroke is commonly known as stroke, and refers to a condition that causes damage to the cerebral vessels, focal (or global) brain tissue, including ischemic stroke and hemorrhagic stroke. After the patient is admitted with suspected stroke symptoms, a doctor performs computed tomography (Computed Tomography, CT) scanning on the patient, and performs preliminary diagnosis and typing on the patient through CT images.
In the traditional technology, the scanning equipment for collecting the image data of the patient is connected with the desktop client used by the doctor through a network cable and a router, and the collected image data of the patient is transmitted to the desktop client used by the doctor in the hospital by utilizing the local area network in the hospital, so that the doctor can diagnose and type the cerebral apoplexy symptoms of the patient.
However, the conventional technique has a problem in that diagnostic efficiency for image data of a patient is low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a brain image processing method, system, computer device, and storage medium that can improve the diagnostic efficiency of video data.
A brain image processing method, the method comprising:
acquiring a brain image to be processed;
inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image;
inputting the brain image into a preset second separation network to obtain each brain region division map corresponding to the brain image;
and analyzing the region of interest map and each brain region division map to obtain a preliminary grading result of the brain image.
In one embodiment, the method further comprises:
Encrypting the brain image and the preliminary grading result through a gateway and then sending the encrypted brain image and the preliminary grading result to a mobile terminal; the mobile terminal is used for decrypting the encrypted brain image and the preliminary grading result and obtaining an analysis result of the user on the decrypted brain image.
In one embodiment, the method further comprises:
acquiring processed data returned by the mobile terminal through the gateway; the processed data are obtained by decrypting the encrypted processed data returned by the mobile terminal by the gateway, and the data are obtained by verifying the decrypted primary grading result by the user.
In one embodiment, the obtaining the preliminary grading result of the brain image according to the region of interest map and the brain region division map includes:
obtaining the corresponding bleeding amount and/or ischemia amount of each brain region according to the region-of-interest map and each brain region partition map;
and obtaining a preliminary grading result of the brain image according to the bleeding amount and/or the ischemia amount corresponding to each brain region.
In one embodiment, the obtaining the preliminary grading result of the brain image according to the bleeding amount and/or the ischemia amount corresponding to each brain region includes:
Obtaining a grading result of each brain region according to the bleeding amount corresponding to each brain region and the bleeding amount threshold preset by each brain region and/or the ischemia amount corresponding to each brain region and the ischemia amount threshold preset by each brain region;
and obtaining a preliminary grading result of the brain image according to the grading result of each brain region.
In one embodiment, the obtaining the preliminary classification result of the brain image according to the classification result of each brain region includes:
determining a target grading result from the grading results of the brain areas;
and determining the target grading result as a preliminary grading result of the brain image.
In one embodiment, the obtaining the corresponding bleeding amount and/or ischemia amount of each brain region according to the region of interest map and each brain region partition map includes:
comparing the region of interest map with the brain region segmentation map to determine the volume of the region of interest corresponding to each brain region;
and obtaining the corresponding bleeding amount and/or ischemia amount of each brain region according to the volume of the region of interest corresponding to each brain region.
A brain image processing system, the system comprising: the system comprises image acquisition equipment, a server, a gateway and a mobile terminal, wherein the image acquisition equipment is connected with the server through a local area network, and the server is connected with the gateway through the local area network; the gateway is connected with the mobile terminal through a wide area network;
The image acquisition equipment is used for acquiring brain images to be processed;
the server is used for executing the image processing method;
the gateway is used for encrypting the brain image and the preliminary grading result and sending the encrypted brain image and the preliminary grading result to the mobile terminal;
the mobile terminal is used for decrypting the encrypted brain image and the preliminary grading result and obtaining an analysis result of the user on the decrypted brain image.
A brain image processing device, the device comprising:
the first acquisition module is used for acquiring a brain image to be processed;
the second acquisition module is used for inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image;
the third acquisition module is used for inputting the brain image into a preset second segmentation network to obtain each brain segmentation map corresponding to the brain image;
and the processing module is used for obtaining a preliminary grading result of the brain image according to the region-of-interest graph and each brain region-separating graph.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
Acquiring a brain image to be processed;
inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image;
inputting the brain image into a preset second separation network to obtain each brain region division map corresponding to the brain image;
and analyzing the region of interest map and each brain region division map to obtain a preliminary grading result of the brain image.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a brain image to be processed;
inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image;
inputting the brain image into a preset second separation network to obtain each brain region division map corresponding to the brain image;
and analyzing the region of interest map and each brain region division map to obtain a preliminary grading result of the brain image.
According to the brain image processing method, the system, the device, the computer equipment and the storage medium, the region-of-interest image of the brain image to be processed can be obtained by inputting the brain image to be processed into the preset first segmentation network, the brain image to be processed is input into the preset second segmentation network, each brain region-of-interest image corresponding to the brain image to be processed can be obtained, the obtained region-of-interest image of the brain image to be processed and each brain region-of-interest image corresponding to the brain image to be processed are analyzed, the preliminary classification result of the brain image can be obtained rapidly, and therefore priority ranking can be carried out according to the preliminary classification result of the brain image to be processed, the brain image with higher priority in the preliminary classification result can be processed preferentially, and the diagnosis efficiency of the brain image to be processed is improved.
Drawings
FIG. 1 is a schematic diagram of an internal structure of a computer device according to one embodiment;
FIG. 2 is a flow chart of a brain image processing method according to an embodiment;
FIG. 3 is a flow chart of a brain image processing method according to another embodiment;
FIG. 4 is a schematic diagram of a brain image processing system according to one embodiment;
FIG. 5 is a schematic diagram of a brain image processing system according to another embodiment;
fig. 6 is a schematic diagram of a brain image processing device according to an embodiment.
Description of the embodiments
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The brain image processing method provided by the embodiment of the application can be applied to the computer equipment shown in fig. 1. The computer device comprises a processor, a memory, and a computer program stored in the memory, wherein the processor is connected through a system bus, and when executing the computer program, the processor can execute the steps of the method embodiments described below. Optionally, the computer device may further comprise a network interface, a display screen and an input means. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, which stores an operating system and a computer program, an internal memory. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. Optionally, the computer device may be a server, may be a personal computer, may also be a personal digital assistant, may also be other terminal devices, such as a tablet computer, a mobile phone, etc., and may also be a cloud or remote server.
Cerebral stroke refers to damage to cerebral vessels, focal (or global) brain tissue, caused by various causes, including ischemic stroke, hemorrhagic stroke, and mixed stroke. When a patient is admitted after suspected cerebral apoplexy symptoms appear, the patient can be preferentially subjected to computer tomography (Computed Tomography, CT) scanning, and the patient is subjected to preliminary diagnosis and typing through the CT images. Since the time to perform a CT scan of a patient greatly affects the treatment of the patient. In order to protect the data resources of the patient from leakage, hospitals tend to use a conservative internal network, a data acquisition end (scanning equipment such as CT (computed tomography)), a database and a desktop client used by a doctor are connected through a network cable and a router, and the system has a complete internal data management system, but the diagnosis mode of the doctor is limited, and the critical patient is difficult to obtain high-priority treatment before manual diagnosis, so that the diagnosis efficiency of the image data of the patient is low.
The following describes the technical scheme of the present invention and how the technical scheme of the present invention solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
In one embodiment, as shown in fig. 2, there is provided a brain image processing method, which is exemplified by the application of the method to the computer device in fig. 1, and includes the steps of:
s201, acquiring a brain image to be processed.
Specifically, the computer device first acquires a brain image to be processed. The brain image to be processed may be a brain computed tomography (Computed Tomography, CT) image, a brain magnetic resonance (Magnetic Resonance, MR) image, a brain magnetic resonance diffusion weighted imaging (Diffusion Weighted Imaging, DWI) image, or a brain magnetic resonance perfusion imaging (Perfusion Imaging, PWI) image. Optionally, the computer device may obtain the brain image to be processed from a PACS (Picture Archiving and Communication Systems, image archiving and communication system), may obtain the brain image to be processed from a RIS (Radioiogy information system, radiological information management system), or may obtain the brain image to be processed from a medical imaging device in real time.
S202, inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image.
Specifically, the computer equipment inputs the brain image to be processed into a preset first segmentation network to obtain a region-of-interest map of the brain image to be processed. It will be appreciated that the region of interest of the brain image to be processed is a focal region in the brain image, optionally the focal region may be an ischemic or hemorrhagic or neoplastic or both. Alternatively, taking the application of the brain image to be processed in the diagnosis of cerebral stroke as an example, the region of interest of the brain image to be processed may be a bleeding region in the brain image or an ischemia region in the brain image. Optionally, before the computer device inputs the brain image to be processed into the preset first segmentation network, windowing normalization processing, skull removing processing and the like can be performed on the brain image to be processed; the windowing normalization processing refers to performing windowing restriction on a brain image to be processed according to information such as window width and window level commonly used in clinic, for example, voxels with HU value smaller than 0 in head CT data of the brain image to be processed are set to be 0, voxels with HU value larger than 80 are set to be 80, value ranges of [0, 80] are linearly mapped to [0, 1], the windowing normalization operation can enhance the contrast of a target, and the head data is normalized, so that the detection difficulty is reduced; the skull removing treatment is to detect and divide the skull part in the head data of the brain image to be treated based on the imaging or artificial intelligence technology, remove the skull and other background elements, and reduce the interference of the brain external tissue on the brain detection. Optionally, after obtaining the region of interest map of the brain image to be processed, the computer device may perform post-processing on the obtained region of interest map, where the post-processing includes a connected domain threshold filtering method and a region growing method; the connected domain threshold filtering method is used for reducing false positive of a segmentation algorithm, separating the connected domain of the interested region graph of the obtained brain image, and setting the connected domain with the volume smaller than T as a background according to a clinically determined volume threshold T to obtain a post-processed interested region graph; the region growing method is used for reducing the incomplete segmentation of the obtained region-of-interest graph by the segmentation algorithm, and the obtained region-of-interest graph can be used as a starting point for carrying out edge repair by using the region growing method, so that the obtained final region-of-interest graph is more attached to a real focus region, and the calculation error is reduced.
And S203, inputting the brain image into a preset second segmentation network to obtain each brain segmentation map corresponding to the brain image.
Specifically, the computer equipment inputs the brain image to be processed into a preset second segmentation network to obtain each brain region segmentation map corresponding to the brain image to be processed. Optionally, the computer device may also perform brain segmentation on the brain image to be processed according to a preset brain segmentation template, so as to obtain each brain segmentation map corresponding to the processed brain image, and optionally, the preset brain segmentation template may be an anatomical automatic labeling (Anatomical Automatic Labeling, AAL) template, or may be another brain segmentation template, for example, an SRI24 template.
S204, analyzing the region of interest map and each brain region map to obtain a preliminary grading result of the brain image.
Specifically, the computer device analyzes the obtained region-of-interest map of the brain image to be processed and each brain region division map corresponding to the brain image to be processed, and obtains a preliminary grading result of the brain image to be processed. Optionally, continuing to take the application of the brain image to be processed to the cerebral apoplexy diagnosis as an example, the computer device may determine the volume of the region of interest corresponding to each brain region in each brain region division map of the brain image to be processed according to the region of interest map of the brain image to be processed, and obtain the preliminary classification result of the brain image to be processed according to the volume of the region of interest corresponding to each brain region in each brain region division map. Optionally, the computer device may further input the brain image to be processed into a preset classification network according to the preset classification network, so as to obtain a preliminary classification result of the brain image to be processed.
In this embodiment, a region of interest map of a brain image to be processed can be obtained by inputting the brain image to be processed into a preset first segmentation network, each brain region map corresponding to the brain image to be processed can be obtained by inputting the brain image to be processed into a preset second segmentation network, the obtained region of interest map of the brain image to be processed and each brain region map corresponding to the brain image to be processed are analyzed, a preliminary classification result of the brain image can be obtained rapidly, and thus, priority ranking can be performed according to the preliminary classification result of the brain image to be processed, and a brain image with higher priority in the preliminary classification result can be processed preferentially, thereby improving the diagnosis efficiency of the brain image to be processed.
In an embodiment, on the basis of the foregoing embodiment, as an optional implementation manner, the foregoing method further includes: encrypting the brain image and the preliminary grading result through a gateway and then sending the encrypted brain image and the preliminary grading result to a mobile terminal; the mobile terminal is used for decrypting the encrypted brain image and the preliminary grading result and obtaining an analysis result of the user on the decrypted brain image.
Specifically, the computer equipment encrypts the brain image to be processed and the preliminary grading result through a gateway and then sends the encrypted brain image and the preliminary grading result to the mobile terminal; the mobile terminal is used for decrypting the encrypted brain image and the preliminary grading result and obtaining an analysis result of the user on the decrypted brain image. Optionally, the gateway may encrypt the brain image to be processed and the preliminary classification result through a Message-Digest (MD 5) encryption Algorithm in a hash encryption Algorithm, may encrypt the brain image to be processed and the preliminary classification result through a 3DES encryption Algorithm of a symmetric encryption Algorithm, or encrypt the brain image to be processed and the preliminary classification result through an RSA encryption Algorithm of an asymmetric encryption Algorithm. Optionally, the analysis result of the mobile terminal user on the decrypted brain image may be the analyzed brain image or a grading grade of the brain image, and it may be understood that if the analysis result is the analyzed brain image, the brain image may be marked with a corresponding grading grade. The mobile terminal comprises at least one mobile device with 5G network access capability, and the mobile device comprises, but is not limited to, a mobile phone, a tablet and the like. The mobile terminal equipment decrypts the encrypted brain image and the preliminary grading result, interprets the decrypted brain image through a program, provides the decrypted brain image for a user of the mobile terminal to read and diagnose, and simultaneously transmits the analysis result of the decrypted brain image by the user of the mobile terminal back to the gateway. The gateway is a computer device with a security function and used for data exchange management, and can comprise at least one computer device, the gateway is simultaneously connected to the local area network and the 5G network, the gateway encrypts the brain image and the preliminary classification result and sends the brain image and the preliminary classification result to the 5G network to be distributed to the mobile terminal for diagnosis of the mobile terminal user, and meanwhile, the gateway receives the analysis result of the decrypted brain image from the mobile terminal user transmitted by the isomorphic 5G communication system. Optionally, the computer device may further obtain an analysis result of the decrypted brain image by the mobile terminal user through the gateway, and input the obtained analysis result of the brain image and the corresponding brain image into a preset memory for storage. Optionally, the computer device may also send the brain image to be processed and the preliminary grading result to a desktop client in the hospital through the local area network, where the desktop client in the hospital includes at least one desktop computer for diagnosis of the patient image and filling of the report, and the desktop client uses the local area network and the computer device to perform communication and data exchange, and the desktop client is a conventional office tool, and has a limited location and flexibility.
In the embodiment, the computer equipment encrypts the brain image to be processed and the preliminary classification result of the brain image through the gateway and then sends the encrypted brain image to the mobile terminal, so that a user of the mobile terminal can analyze and diagnose the brain image to be processed according to the preliminary classification result of the brain image to be processed in time, and the diagnosis efficiency of the brain image to be processed is improved; in addition, the brain image and the preliminary classification result of the brain image are encrypted through the gateway, so that the safety of the brain image and the preliminary classification result of the brain image in the transmission process is ensured.
In some scenarios, the preliminary classification result of the brain image to be processed obtained by the computer device may be a result with a low criticality, so that after the preliminary classification result of the brain image to be processed and the brain image to be processed is sent to the mobile terminal, the mobile terminal can verify the preliminary classification result and then can return the processed data. In an embodiment, on the basis of the foregoing embodiment, as an optional implementation manner, the foregoing method further includes: acquiring processed data returned by the mobile terminal through a gateway; the processed data are obtained by decrypting the encrypted processed data returned by the mobile terminal by the gateway, and the data comprise data obtained by verifying the decrypted primary grading result by a user.
Specifically, the computer equipment acquires the processed data returned by the mobile terminal through a gateway; the data after processing is obtained by decrypting the encrypted processed data returned by the mobile terminal by the gateway, and the data comprises data obtained by verifying the decrypted primary grading result by the mobile terminal user. For example, the decrypted preliminary classification result is that the critical degree of the brain image to be processed is low, and after the received brain image and the preliminary classification result are verified and determined that the preliminary classification result is accurate, the brain image corresponding to the preliminary classification result and the verification result of the preliminary classification result can be returned to the computer device through the network. Alternatively, the encrypted processing data returned by the mobile terminal may be obtained by a Message-Digest (MD 5) encryption Algorithm in a hash encryption Algorithm, or may be obtained by a 3DES encryption Algorithm of a symmetric encryption Algorithm, or may be obtained by an RSA encryption Algorithm of an asymmetric encryption Algorithm.
In this embodiment, the computer device obtains the data obtained after the mobile terminal user verifies the decrypted preliminary classification result returned by the mobile terminal through the gateway, and can timely obtain the data obtained after the mobile terminal user verifies the preliminary classification result of the brain image to be processed, thereby improving the diagnosis efficiency of the brain image to be processed.
In one embodiment, as shown in fig. 3, based on the embodiment, as an alternative implementation manner, the step S204 includes:
s301, obtaining the corresponding bleeding amount and/or ischemia amount of each brain region according to the region-of-interest map and each brain region partition map.
Specifically, the computer equipment obtains the corresponding bleeding amount and/or ischemia amount of each brain region according to the interested region graph of the brain image to be processed and each brain region graph of the brain image to be processed. Optionally, the computer device may compare the region of interest map of the brain image to be processed with each brain region segmentation map of the brain image to be processed, determine a volume of the region of interest corresponding to each brain region of the brain image to be processed, and obtain the bleeding amount and/or the ischemia amount corresponding to each brain region according to the volume of the region of interest corresponding to each brain region. It should be noted that, the computer device inputs the brain image to be processed into a preset first segmentation network, so as to obtain the region of interest map of the brain image to be processed, and meanwhile, also obtain the abnormal type corresponding to the brain image to be processed, and optionally, the abnormal type corresponding to the brain image to be processed can include ischemic cerebral apoplexy, hemorrhagic cerebral apoplexy and mixed cerebral apoplexy. For example, if the computer device determines that the type of abnormality corresponding to the brain image to be processed is ischemic stroke, the computer device obtains the ischemia corresponding to each brain region according to the region of interest map and each brain region map of the brain image to be processed; if the computer equipment determines that the abnormal type corresponding to the brain image to be processed is hemorrhagic stroke, the computer equipment obtains the hemorrhage amount corresponding to each brain region according to the interested region graph and each brain region graph of the brain image to be processed; if the computer equipment determines that the abnormal type corresponding to the brain image to be processed is the mixed cerebral apoplexy, the computer equipment obtains the ischemia and the hemorrhage corresponding to each brain region according to the interested region graph and each brain region graph of the brain image to be processed.
S302, obtaining a preliminary grading result of brain images according to the bleeding amount and/or the ischemia amount corresponding to each brain region.
Specifically, the computer equipment obtains a preliminary grading result of the brain image to be processed according to the bleeding amount and/or the ischemia amount corresponding to each brain region of the brain image to be processed. Optionally, the computer device may obtain a classification result of each brain region according to the bleeding amount corresponding to each brain region and the bleeding amount threshold preset for each brain region, and/or the ischemia amount corresponding to each brain region and the ischemia amount threshold preset for each brain region, determine a target classification result from the classification results of each brain region, and determine the determined target classification result as a preliminary classification result of the brain image to be processed. For example, the computer device may compare the amount of bleeding corresponding to each brain region with a preset amount of bleeding threshold for each brain region, and if the amount of bleeding corresponding to each brain region is greater than the preset amount of bleeding threshold for each brain region, determine that the classification result for the brain region is critical; if the corresponding bleeding amount of each brain region is smaller than or equal to the preset bleeding amount threshold value of each brain region, determining that the classification result of the brain region is not critical, if one classification result in the classification results of each brain region of the brain image to be processed is critical, determining that the classification result of the brain region is a target classification result, and determining that the target classification result is a target classification result, namely, determining that the target classification result is critical. It should be noted that, continuing to take the application of the brain image to be processed to the diagnosis of cerebral apoplexy as an example, the situation that the cross-brain-area hemorrhage and/or ischemia may occur in the brain image to be processed, at this time, the computer device may count the number of the cross-brain-area hemorrhage and/or ischemia brain areas, if the number of the cross-brain-area hemorrhage and/or ischemia exceeds a preset threshold, it is determined that the primary grading result corresponding to the brain image to be processed is critical, and, for example, if the number of the cross-brain-area hemorrhage or ischemia is three, and the preset threshold is one, it is determined that the primary grading result corresponding to the brain image to be processed is critical by the computer device; optionally, the computer device may also determine the primary grading result corresponding to the brain image to be processed as critical by determining the amount of bleeding and/or ischemia in each of the brain regions that bleed and/or ischemia in each of the brain regions, comparing the amount of bleeding and/or ischemia in each of the brain regions with a preset amount of bleeding and/or ischemia threshold corresponding to each of the brain regions, and if the amount of bleeding and/or ischemia in one of the brain regions exceeds the preset amount of bleeding and/or ischemia threshold.
In this embodiment, the computer device may accurately obtain the amount of bleeding and/or ischemia corresponding to each brain region according to the region-of-interest map of the brain image to be processed and each brain region map of the brain image to be processed, and further may accurately obtain the preliminary classification result of the brain image to be processed according to the amount of bleeding and/or ischemia corresponding to each brain region, thereby improving the accuracy of the obtained preliminary classification result of the brain image to be processed.
It should be understood that, although the steps in the flowcharts of fig. 2-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-3 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, as shown in FIG. 4, there is provided a brain image processing system comprising: the system comprises image acquisition equipment, a server, a gateway and a mobile terminal; the image acquisition equipment is connected with the server through a local area network, the server is connected with the gateway through the local area network, and the gateway is connected with the mobile terminal through a wide area network; the image acquisition equipment is used for acquiring brain images to be processed; a server for executing the image processing method of the above embodiment; the gateway is used for encrypting the brain image and the preliminary grading result and transmitting the encrypted brain image and the preliminary grading result to the mobile terminal; the mobile terminal is used for decrypting the encrypted brain image and the preliminary grading result and acquiring an analysis result of the user on the decrypted brain image.
Specifically, the image acquisition device may include an image acquisition device of CT, magnetic resonance (Magnetic Resonance, MR) or the like, by which brain images to be processed are acquired;
the server is configured to execute the brain image processing method in the foregoing embodiment, where the server may include at least one computer with better performance, or may be a distributed computing cluster, so as to perform common tasks such as data flow management, log statistics, and so on. The server communicates with other modules only through an internal local area network, so that external interference and data leakage are reduced.
The gateway is used for encrypting the brain image to be processed and the preliminary grading result of the brain image to be processed, and sending the encrypted brain image and the preliminary grading result to the mobile terminal. Optionally, the gateway may include at least one computer, and is connected to the local area network and the 5G network simultaneously, and the gateway performs encryption control on the brain image to be processed and the preliminary classification result of the brain image to be processed through the program, and sends the brain image to the 5G network to be distributed to the mobile terminal for diagnosis of the user of the mobile terminal; meanwhile, the diagnosis report of the mobile terminal user transmitted back by the isomorphic 5G communication system needs to be received, sent to the local area network and transmitted back to the server for management.
The mobile terminal is used for decrypting the encrypted brain image and the preliminary grading result and acquiring an analysis result of the user on the decrypted brain image. Optionally, the mobile terminal includes at least one mobile device with 5G network access capability, including but not limited to a cell phone, tablet, etc. The mobile terminal reads the brain image to be processed and the preliminary grading result of the brain image to be processed, which are transmitted by the gateway, through the program, and provides the preliminary grading result for the user of the mobile terminal to read and diagnose, and simultaneously transmits the diagnosis report of the user of the mobile terminal back to the gateway.
In the embodiment, the brain image processing system transmits the preliminary classification result of the brain image to be processed to the mobile terminal through the gateway, so that the working pressure of a user at the mobile terminal is greatly reduced, and the diagnosis efficiency of the brain image to be processed is improved; and secondly, the brain image to be processed and the preliminary grading result of the brain image to be processed are sent to the mobile terminal through the gateway, so that the diagnosis path of the brain image to be processed is expanded, and the diagnosis efficiency of the brain image to be processed is further improved.
In one embodiment, as shown in fig. 5, the brain image processing system may further include a memory and a desktop client, where the memory is connected to the server through a local area network, and the desktop client is connected to the server through a local area network; the memory is used for storing the brain image to be processed, the preliminary grading result of the brain image to be processed and the analysis result of the brain image to be processed; the desktop client is used for receiving the brain image to be processed and the preliminary grading result of the brain image to be processed, which are sent by the server, and acquiring the analysis result of the brain image to be processed by the user of the desktop client.
Specifically, the memory is used for storing the brain image to be processed and the preliminary grading result of the brain image to be processed. Optionally, the memory may include at least one device with more storage space, or may be a distributed storage cluster, configured to store the brain image to be processed, a preliminary classification result of the brain image to be processed, and an analysis result of the brain image to be processed. It should be noted that, the analysis result of the brain image to be processed stored in the memory may be an analysis result of the brain image to be processed by the mobile terminal user, or may be an analysis result of the brain image to be processed by the desktop client user.
The desktop client side adopts a local area network and a server to carry out communication and data exchange, and is used for receiving the brain image to be processed and the preliminary classification result of the brain image to be processed, which are sent by the server, and obtaining the analysis result of the brain image to be processed by the user of the desktop client side. Alternatively, the desktop client may comprise at least one desktop computer. It will be appreciated that desktop clients are a conventional office tool for users, with limited location and flexibility.
In this embodiment, the memory included in the brain image processing system may store the brain image to be processed, the preliminary classification result of the brain image to be processed, and the analysis result of the brain image to be processed, so as to avoid data loss; in addition, the desktop client side included in the image processing system can also receive the brain image to be processed and the preliminary classification result of the brain image to be processed, which are sent by the server, so that a user of the desktop client side can analyze the brain image to be processed, and the efficiency of analysis and diagnosis of the brain image to be processed is improved.
In one embodiment, as shown in fig. 6, there is provided a brain image processing apparatus including: the device comprises a first acquisition module, a second acquisition module, a third acquisition module and a processing module, wherein:
And the first acquisition module is used for acquiring the brain image to be processed.
The second acquisition module is used for inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image.
And the third acquisition module is used for inputting the brain image into a preset second segmentation network to obtain each brain region segmentation map corresponding to the brain image.
And the processing module is used for analyzing the region-of-interest graph and each brain region graph to obtain a preliminary grading result of the brain image.
The brain image processing device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the above apparatus further includes a sending module, where:
the sending module is used for encrypting the brain image and the preliminary grading result through the gateway and then sending the encrypted brain image and the preliminary grading result to the mobile terminal; the mobile terminal is used for decrypting the encrypted brain image and the preliminary grading result and obtaining an analysis result of the user on the decrypted brain image.
The brain image processing device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the above apparatus further includes a fourth acquisition module, where:
A fourth obtaining module, configured to obtain, through a gateway, processed data returned by the mobile terminal; the processed data are obtained by decrypting the encrypted processed data returned by the mobile terminal by the gateway, and the data comprise data obtained by verifying the decrypted primary grading result by a user.
The brain image processing device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the above processing module includes a first acquiring unit and a second acquiring unit, where:
and the first acquisition unit is used for obtaining the corresponding bleeding amount and/or ischemia amount of each brain region according to the region-of-interest map and each brain region map.
And the second acquisition unit is used for obtaining a preliminary grading result of the brain image according to the bleeding amount and/or the ischemia amount corresponding to each brain region.
The brain image processing device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the second obtaining unit is specifically configured to obtain a classification result of each brain region according to a bleeding amount corresponding to each brain region and a preset bleeding amount threshold of each brain region, and/or an ischemia amount corresponding to each brain region and a preset ischemia amount threshold of each brain region; and obtaining a preliminary grading result of the brain image according to the grading result of each brain region.
The brain image processing device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the second obtaining unit is specifically configured to determine a target classification result from classification results of each brain region; and determining the target grading result as a preliminary grading result of the brain image.
The brain image processing device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
On the basis of the above embodiment, optionally, the first obtaining unit is specifically configured to compare the region of interest map with each brain region segmentation map, and determine a volume of the region of interest corresponding to each brain region; and obtaining the corresponding bleeding amount and/or ischemia amount of each brain region according to the volume of the region of interest corresponding to each brain region.
The brain image processing device provided in this embodiment may execute the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein.
For specific limitations of the brain image processing device, reference may be made to the above limitation of the brain image processing method, and no further description is given here. The respective modules in the above brain image processing apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring a brain image to be processed;
inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image;
inputting the brain image into a preset second segmentation network to obtain each brain region segmentation map corresponding to the brain image;
and obtaining a preliminary grading result of the brain image according to the region-of-interest graph and each brain region-separating graph.
The computer device provided in the foregoing embodiments has similar implementation principles and technical effects to those of the foregoing method embodiments, and will not be described herein in detail.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a brain image to be processed;
inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image;
inputting the brain image into a preset second segmentation network to obtain each brain region segmentation map corresponding to the brain image;
and obtaining a preliminary grading result of the brain image according to the region-of-interest graph and each brain region-separating graph.
The computer readable storage medium provided in the above embodiment has similar principle and technical effects to those of the above method embodiment, and will not be described herein.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A brain image processing method, the method comprising:
acquiring a brain image to be processed;
inputting the brain image into a preset first segmentation network to obtain a region-of-interest map of the brain image; wherein the region of interest is a hemorrhagic and/or ischemic range;
inputting the brain image into a preset second separation network to obtain each brain region division map corresponding to the brain image;
Obtaining the bleeding amount and/or ischemia amount corresponding to each brain region according to the region-of-interest map and each brain region division map, and determining the preliminary classification result of the brain image as critical if one classification result is critical according to the bleeding amount corresponding to each brain region and the preset bleeding amount threshold of each brain region and/or the ischemia amount corresponding to each brain region and the preset ischemia amount threshold of each brain region; the grading result includes critical and non-critical.
2. The method according to claim 1, wherein the method further comprises:
encrypting the brain image and the preliminary grading result through a gateway and then sending the encrypted brain image and the preliminary grading result to a mobile terminal; the mobile terminal is used for decrypting the encrypted brain image and the preliminary grading result and obtaining an analysis result of the user on the decrypted brain image.
3. The method according to claim 2, wherein the method further comprises:
acquiring processed data returned by the mobile terminal through the gateway; the processed data are obtained by decrypting the encrypted processed data returned by the mobile terminal by the gateway, and the data are obtained by verifying the decrypted primary grading result by the user.
4. The method according to claim 1, wherein the method further comprises:
and if the grading result of each brain region is not critical, determining the preliminary grading result of the brain image to be not critical.
5. The method according to claim 2, wherein the encrypted brain image and the preliminary classification result are obtained by encrypting the brain image and the preliminary classification result by any one of an information-digest encryption algorithm among hash encryption algorithms, a 3DES encryption algorithm of a symmetric encryption algorithm, and an RSA encryption algorithm of an asymmetric encryption algorithm.
6. The method according to claim 1, wherein the obtaining the grading result of each brain region according to the bleeding amount corresponding to each brain region and the bleeding amount threshold preset for each brain region, and/or the ischemia amount corresponding to each brain region and the ischemia amount threshold preset for each brain region includes:
if the bleeding amount corresponding to each brain region is greater than the bleeding amount threshold value and/or the ischemia amount corresponding to each brain region is greater than the ischemia amount threshold value, determining that the grading result of the brain region is critical; or alternatively, the process may be performed,
and if the bleeding amount corresponding to each brain region is smaller than or equal to the bleeding amount threshold value and/or the ischemia amount corresponding to each brain region is smaller than or equal to the ischemia amount threshold value, determining that the grading result of the brain region is not critical.
7. The method according to claim 4, wherein obtaining the corresponding bleeding amount and/or ischemia amount of each brain region according to the region of interest map and each brain region map comprises:
comparing the region of interest map with the brain region segmentation map to determine the volume of the region of interest corresponding to each brain region;
and obtaining the corresponding bleeding amount and/or ischemia amount of each brain region according to the volume of the region of interest corresponding to each brain region.
8. A brain image processing system, the system comprising: the system comprises image acquisition equipment, a server, a gateway and a mobile terminal, wherein the image acquisition equipment is connected with the server through a local area network, and the server is connected with the gateway through the local area network; the gateway is connected with the mobile terminal through a wide area network;
the image acquisition equipment is used for acquiring brain images to be processed;
the server for performing the brain image processing method according to any one of claims 1 to 7;
the gateway is used for encrypting the brain image and the preliminary grading result and sending the encrypted brain image and the preliminary grading result to the mobile terminal;
The mobile terminal is used for decrypting the encrypted brain image and the preliminary grading result and obtaining an analysis result of the user on the decrypted brain image.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010200838.0A CN111445451B (en) | 2020-03-20 | 2020-03-20 | Brain image processing method, system, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010200838.0A CN111445451B (en) | 2020-03-20 | 2020-03-20 | Brain image processing method, system, computer device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111445451A CN111445451A (en) | 2020-07-24 |
| CN111445451B true CN111445451B (en) | 2023-04-25 |
Family
ID=71629559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010200838.0A Active CN111445451B (en) | 2020-03-20 | 2020-03-20 | Brain image processing method, system, computer device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111445451B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529868B (en) * | 2020-12-10 | 2023-06-27 | 上海联影医疗科技股份有限公司 | Image analysis method, image analysis device, computer equipment and storage medium |
| CN112508953B (en) * | 2021-02-05 | 2021-05-18 | 四川大学 | Meningioma rapid segmentation qualitative method based on deep neural network |
| CN114601486B (en) * | 2022-03-07 | 2023-05-02 | 深圳市澈影医生集团有限公司 | Detection system for acute ischemic cerebral apoplexy |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106887039A (en) * | 2017-02-28 | 2017-06-23 | 成都金盘电子科大多媒体技术有限公司 | The three-D imaging method and system of a kind of organ and focus based on medical image |
| CN108852627A (en) * | 2018-07-18 | 2018-11-23 | 广州市妇女儿童医疗中心（广州市妇幼保健院、广州市儿童医院、广州市妇婴医院、广州市妇幼保健计划生育服务中心） | A kind of intelligent identifying system |
| CN109003299A (en) * | 2018-07-05 | 2018-12-14 | 北京推想科技有限公司 | A method of the calculating cerebral hemorrhage amount based on deep learning |
| CN110336809A (en) * | 2019-06-28 | 2019-10-15 | 国网内蒙古东部电力有限公司 | A kind of method that airborne FPGA accelerates image analysis processing system parallel |
| CN110738643A (en) * | 2019-10-08 | 2020-01-31 | 上海联影智能医疗科技有限公司 | Method for analyzing cerebral hemorrhage, computer device and storage medium |
| CN110840468A (en) * | 2019-11-18 | 2020-02-28 | 深圳市铱硙医疗科技有限公司 | Autism risk assessment method and device, terminal device and storage medium |
-
2020
- 2020-03-20 CN CN202010200838.0A patent/CN111445451B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106887039A (en) * | 2017-02-28 | 2017-06-23 | 成都金盘电子科大多媒体技术有限公司 | The three-D imaging method and system of a kind of organ and focus based on medical image |
| CN109003299A (en) * | 2018-07-05 | 2018-12-14 | 北京推想科技有限公司 | A method of the calculating cerebral hemorrhage amount based on deep learning |
| CN108852627A (en) * | 2018-07-18 | 2018-11-23 | 广州市妇女儿童医疗中心（广州市妇幼保健院、广州市儿童医院、广州市妇婴医院、广州市妇幼保健计划生育服务中心） | A kind of intelligent identifying system |
| CN110336809A (en) * | 2019-06-28 | 2019-10-15 | 国网内蒙古东部电力有限公司 | A kind of method that airborne FPGA accelerates image analysis processing system parallel |
| CN110738643A (en) * | 2019-10-08 | 2020-01-31 | 上海联影智能医疗科技有限公司 | Method for analyzing cerebral hemorrhage, computer device and storage medium |
| CN110840468A (en) * | 2019-11-18 | 2020-02-28 | 深圳市铱硙医疗科技有限公司 | Autism risk assessment method and device, terminal device and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| H.S. Bhadauria et al..An integrated method for hemorrhage segmentation from brain CT Imaging.《Computers and Electrical Engineering》.2013,第1527-1536页. * |
| Natasha Ironside, MBChB et al..Fully Automated Segmentation Algorithm for Hematoma Volumetric Analysis in Spontaneous Intracerebral Hemorrhage.《2019 American Heart Association, Inc》.2019,第3416-3423页. * |
| 麦麦提力.米吉提.动脉瘤性蛛网膜下腔出血临床流行病学特征分析及其血后脑血管痉挛影像因素研究.《中国博士学位论文全文数据库 医药卫生科技辑》.2016,E070-6. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111445451A (en) | 2020-07-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111445451B (en) | Brain image processing method, system, computer device and storage medium | |
| US10971263B2 (en) | Methods and apparatus for recording anonymized volumetric data from medical image visualization software | |
| WO2022033220A1 (en) | Face liveness detection method, system and apparatus, computer device, and storage medium | |
| US11790672B2 (en) | Image processing method, microscope, image processing system, and medium based on artificial intelligence | |
| US10817753B2 (en) | Learning assistance device, method of operating learning assistance device, learning assistance program, learning assistance system, and terminal device | |
| JP2022508152A (en) | Systems and methods for tracking protected health information, accessing it, and merging it | |
| US10380739B2 (en) | Breast cancer detection | |
| CN111951274A (en) | Image segmentation method, system, readable storage medium and device | |
| CN112348838B (en) | Method and system for image analysis | |
| Castiglione et al. | On-board format-independent security of functional magnetic resonance images | |
| CN111951276A (en) | Image segmentation method and device, computer equipment and storage medium | |
| US11132793B2 (en) | Case-adaptive medical image quality assessment | |
| CN112527923A (en) | Unstructured data storage method and device, computer equipment and storage medium | |
| EP3890312A1 (en) | Distributed image analysis method and system, and storage medium | |
| US20210097678A1 (en) | Computed tomography medical imaging spine model | |
| CN113158773B (en) | Training method and training device for living body detection model | |
| CN111027469B (en) | Human body part recognition method, computer device, and readable storage medium | |
| JP2023507246A (en) | Method and system for remote analysis of medical image records | |
| CN112786163A (en) | Ultrasonic image processing and displaying method and system and storage medium | |
| US20210093278A1 (en) | Computed tomography medical imaging intracranial hemorrhage model | |
| CN110825693A (en) | Medical data storage method, device and readable storage medium | |
| CN110852384A (en) | Medical image quality detection method, device and storage medium | |
| CN111369557A (en) | Image processing method, image processing device, computing equipment and storage medium | |
| CN114820576A (en) | Mammary gland feature extraction and detection model training method and device | |
| CN113052044A (en) | Method, apparatus, computing device, and medium for recognizing iris image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |